Deep Learning and XAI Techniques for Anomaly Detection

Part 3 – Evaluating an Explainable Deep Learning Anomaly Detector

Part 3 further elaborates on the different dimensions of these XAI techniques. By the end of Part 3, you will have enhanced your skills by analyzing XAI approaches, gauging the extent of interpretability, and evaluating the quality of explanations based on four fundamental principles for XAI systems by the National Institute of Standards and Technology (NIST).

This part comprises the following chapters:

• Chapter 6, Differentiating Intrinsic versus Post Hoc Explainability
• Chapter 7, Backpropagation versus Perturbation Explainability
• Chapter 8, Model-Agnostic versus Model-Specific Explainability
• Chapter 9, Explainability Evaluation Schemes